Skip to main content
Glama

DepScope

Package Intelligence for AI Agents. Stops AI coding agents (Claude, ChatGPT, Cursor, Windsurf, Copilot, Cline) from installing hallucinated, deprecated, or malicious packages across 19 ecosystems.

→ Live at depscope.dev · 8.4M+ packages · 42K+ vulnerabilities (99% EPSS-enriched) · zero auth · free


Quick start (MCP)

Claude Desktop / Cursor / Windsurf — remote

{
  "mcpServers": {
    "depscope": {
      "url": "https://mcp.depscope.dev/mcp"
    }
  }
}

Claude Code / local — stdio

{
  "mcpServers": {
    "depscope": {
      "command": "npx",
      "args": ["-y", "depscope-mcp"]
    }
  }
}

The MCP server source is at cuttalo/depscope-mcp (AGPL-3.0).


Related MCP server: mcp-dep-tools

What it does

22 MCP tools across 19 package ecosystems:

npm · pypi · cargo · go · composer · maven · nuget · rubygems · pub · hex · swift · cocoapods · cpan · hackage · cran · conda · homebrew · jsr · julia

Tool

Purpose

check_package

Full safety check: deprecation · vulnerabilities · health · recommendation

check_malicious

Malicious-package detector

check_typosquat

Typosquat detection vs popular names

package_exists

Hallucination detector (404 = LLM invented it)

get_health_score

0–100 health score with breakdown

get_vulnerabilities

Vulnerabilities + severity scoring

find_alternatives

Suggested alternatives for deprecated/abandoned packages

get_breaking_changes

Major-version migration notes

get_known_bugs

Known issues for a package

compare_packages

Side-by-side comparison

check_compatibility

Stack-level compatibility check

resolve_error

Error message → likely cause + fix

install_command

Verified install command for the target ecosystem

get_latest_version

Latest stable version + maturity signal

pin_safe

Suggested safe version pin

get_trust_signals

Multi-signal trust score

get_migration_path

Step-by-step upgrade plan

scan_project

Bulk scan of dependency manifests

check_bulk

Fast pre-flight filter for batches

get_trending

Trending packages by ecosystem

get_package_prompt

Compact LLM-friendly summary

contact_depscope

Report a missing package or false positive


REST API

Same data, plain HTTPS — no MCP client needed.

curl https://depscope.dev/api/check/npm/lodash
curl https://depscope.dev/api/check/pypi/requests
curl https://depscope.dev/api/check/cargo/serde

Full reference: depscope.dev/integrate


Why

LLMs frequently invent package names that look real but don't exist (fastapi-turbo, lodahs, tokio-stream-extras). When an agent tries to install one, it can hit an attacker's typosquat. DepScope verifies every package before install.

Read more: depscope.dev/why


Pricing

Free. No auth required. Generous rate limits.

If you need higher quotas, SLA, or on-prem deployment, contact us at depscope@cuttalo.com.


Open source vs proprietary

This repository is a landing page with documentation only.

This split lets us keep the client free, auditable, and community-extensible while sustaining the infrastructure that powers it.



License

This README and accompanying landing files: CC-BY-4.0. MCP client SDK: AGPL-3.0 (see cuttalo/depscope-mcp). Backend service: proprietary.


Built by Cuttalo srl · Italy 🇮🇹

Available Tools

22 tools
check_bulkA
Read-onlyIdempotent
Inspect

Fast pre-flight filter for a batch of (ecosystem, package) pairs. DB-only, <100ms for 100 items. USE WHEN: about to emit npm install a b c … or pip install a b c … — catches hallucinated names, stdlib, typos, and known-bad in ONE call. NOT a dep-tree audit (use scan_project for that). RETURNS: per-item {status: exists|stdlib|malicious|typosquat_suspect|historical_incident|unknown}.

Inputs: items (required).

check_compatibilityA
Read-onlyIdempotent
Inspect

Is this specific multi-package version combo verified to work together? USE WHEN: pinning a stack (next@15 + react@19 + node@22); before recommending a version matrix. RETURNS: {compatible, conflicts[], notes}.

Inputs: packages (required).

check_maliciousA
Read-onlyIdempotent
Inspect

Supply-chain malware check against OpenSSF/OSV. USE WHEN: about to suggest install of an unvetted/unfamiliar package; name came from a blog/tutorial. Call BEFORE check_package for untrusted pkgs. RETURNS: {is_malicious, threat_tier, source}.

Inputs: ecosystem (required), package (required).

check_packageA
Read-onlyIdempotent
Inspect

Full machine-readable JSON report (~2k tokens). USE WHEN: you need to programmatically parse specific fields (CI gating, UI, sub-field extraction). Otherwise prefer get_package_prompt. RETURNS: {package, health:{score}, vulnerabilities[], latest, deprecated, maintainers, recommendation}.

Inputs: ecosystem (required), package (required), version.

check_typosquatA
Read-onlyIdempotent
Inspect

Typosquat detector. USE WHEN: name differs from a well-known package by 1-2 chars (lodsh, reqeusts); copy-paste from unreliable source; downloads near zero but name looks familiar. RETURNS: {is_typosquat, likely_target, confidence}.

Inputs: ecosystem (required), package (required).

compare_packagesA
Read-onlyIdempotent
Inspect

Side-by-side comparison (health, vulns, downloads, maintainers, last release) of 2-10 packages in the same ecosystem. USE WHEN: 'X vs Y' / 'should I pick X or Y'. RETURNS: table-shaped JSON, one row per package.

Inputs: ecosystem (required), packages (required).

contact_depscopeAInspect

Inbound ticket: bug/listing/security/anomaly/partnership. USE WHEN: reporting wrong data (bug), requesting a new pkg/ecosystem index (listing), disclosing a DepScope security issue (security), flagging a concrete mismatch in another tool's output vs. authoritative source (anomaly — provide tool_called+observed+expected), or partnership/press (partnership). RETURNS: {ticket_id} or {anomaly_id}.

Inputs: kind, email, subject, body, +9 more.

find_alternativesA
Read-onlyIdempotent
Inspect

Curated replacements for deprecated/unhealthy packages, including stdlib built-ins (e.g. fs.rm for rimraf). USE WHEN: pkg flagged AVOID/URGENT; 'what to use instead of X'; before guessing a replacement name. RETURNS: {alternatives[]: {name, reason, is_stdlib}}.

Inputs: ecosystem (required), package (required).

get_breaking_changesA
Read-onlyIdempotent
Inspect

Breaking changes between two majors of the SAME package (next@14→15). USE WHEN: user is bumping a major; before recommending a major upgrade. Different from get_migration_path (same pkg vs. different pkg). RETURNS: {breaking_changes[]: {area, description, hint}}.

Inputs: ecosystem (required), package (required), from_version, to_version.

get_health_scoreA
Read-onlyIdempotent
Inspect

Single 0-100 health score — cheapest go/no-go gate (>=70 safe). USE WHEN: CI gating or pkg already screened for malware/typos. NOT a first screen — run check_malicious + check_typosquat first. For a verbal verdict use get_package_prompt. RETURNS: {score, verdict}.

Inputs: ecosystem (required), package (required).

get_known_bugsA
Read-onlyIdempotent
Inspect

Non-CVE known bugs for a specific package version. USE WHEN: unexpected behavior that is NOT a security issue; a pinned version misbehaves. RETURNS: {bugs[]: {title, fixed_in, workaround}}.

Inputs: ecosystem (required), package (required), version.

get_latest_versionA
Read-onlyIdempotent
Inspect

Latest published version + deprecation flag — the cheapest call. USE WHEN: only a version string matters (pinning a dep, answering 'what version of X'). If you also need health/vulns use check_package. RETURNS: {latest, deprecated, published_at}.

Inputs: ecosystem (required), package (required).

get_migration_pathA
Read-onlyIdempotent
Inspect

Prescriptive migration plan between DIFFERENT packages — rationale + literal code diff + breaking changes + effort minutes. USE WHEN: replacing request→axios, moment→dayjs, flask→fastapi, etc.; both endpoints known. RETURNS: {rationale, diff, breaking_changes[], estimated_minutes}.

Inputs: ecosystem (required), from_package (required), to_package (required).

get_package_promptA
Read-onlyIdempotent
Inspect

LLM-optimised package brief — plain text ~300 tokens (~75% cheaper than JSON). Verdict (SAFE/AVOID/URGENT/MALICIOUS) + health + vulns + alternatives + maintainer alerts. USE WHEN: you want to reason over a package and drop the output directly in context; 'is X safe'. PREFER THIS over check_package in 95% of LLM cases. RETURNS: plain-text brief.

Inputs: ecosystem (required), package (required).

get_trust_signalsA
Read-onlyIdempotent
Inspect

One-call aggregate of ALL non-CVE supply-chain trust signals: maintainer trust (bus factor, ownership changes), OpenSSF Scorecard, quality (criticality, release velocity, publish security), and SLSA/Sigstore provenance. USE WHEN: deep-vetting a package beyond CVEs (hardened/regulated env, SBOM/compliance, small-pkg ownership review, choosing between healthy candidates). Runs 4 backend endpoints in parallel. RETURNS: {maintainer, scorecard, quality, provenance} — each may be null if its backend call failed.

Inputs: ecosystem (required), package (required).

get_vulnerabilitiesA
Read-onlyIdempotent
Inspect

CVE/OSV advisories affecting the latest (or specified) version. USE WHEN: security-sensitive project; user asks 'any CVEs in X'; you already know the pkg exists. RETURNS: {vulnerability_count, vulnerabilities[]: {id, severity, cvss, fixed_in}}.

Inputs: ecosystem (required), package (required).

install_commandA
Read-onlyIdempotent
Inspect

Canonical install command(s) across every package manager of the ecosystem (npm/pnpm/yarn/bun, pip/uv/poetry, cargo, go, composer, maven+gradle, nuget, …). USE WHEN: emitting an install line and you want correct flags. RETURNS: {primary, variants[]}.

Inputs: ecosystem (required), package (required), version.

package_existsA
Read-onlyIdempotent
Inspect

Boolean registry existence check. USE WHEN: about to emit a package name in an install command but unsure it exists; verifying a name generated from training data. RETURNS: {exists}.

Inputs: ecosystem (required), package (required).

pin_safeA
Read-onlyIdempotent
Inspect

Highest version below the chosen CVE severity tier, respecting a semver constraint. USE WHEN: writing a package.json/requirements.txt line; resolving dependabot by lowest-risk patched version. RETURNS: {recommended_version, walk_log[]}.

Inputs: ecosystem (required), package (required), min_severity, constraint, +1 more.

resolve_errorA
Read-onlyIdempotent
Inspect

Map error OR free-text query to a verified fix. USE WHEN: user pastes a concrete error/stack (ENOENT, ImportError, build failure) — pass error. OR user describes a symptom ('webpack slow', 'pip stuck') — pass query. Always prefer this over guessing a fix. RETURNS: exact-match {status, solution, confidence, source_url} or search results [{title, summary, source_url}].

Inputs: error, query, context, limit.

scan_projectA
Read-onlyIdempotent
Inspect

Full dep-list audit with per-package health+vulns and prioritized actions (REMOVE NOW / URGENT / REPLACE / REVIEW). Accepts EITHER {ecosystem, packages:[name@ver, …]} (up to 100, returns JSON) OR {packages:[{ecosystem, package}, …]} (up to 50, mixed ecosystems, returns text brief). USE WHEN: user pastes package.json/requirements.txt; 'is my stack OK'. Unlike check_bulk this fetches full health/vulns. RETURNS: JSON or text per shape.

Inputs: packages (required), ecosystem.

Tool Schema Changelog

Recent tool additions, removals, and schema changes observed during successful MCP inspections.

Loading tool schema changelog…

    TDQS

    A4/5.0

    Scored across 22 tools

    Disambiguation5/5

    Each tool has a clearly distinct purpose: checks for typosquatting, malware, compatibility, health, vulnerabilities, etc. Even similar tools like `check_package` and `get_package_prompt` are differentiated by output format (JSON vs text) and use case.

    Naming Consistency4/5

    Most tools follow a verb_noun pattern (e.g., `check_malicious`, `get_latest_version`), but a few like `package_exists` (noun_verb) and `install_command` (verb_noun but combined) deviate slightly. The pattern is mostly consistent with lowercase underscores.

    Tool Count4/5

    With 22 tools, the server covers a wide range of dependency analysis needs. While slightly above the typical 3-15 range, each tool serves a specific, non-redundant purpose, making the count appropriate for its comprehensive scope.

    Completeness5/5

    The tool set covers nearly the entire lifecycle of package evaluation: existence, health, security, compat, migration, alternatives, trending, error resolution, and project audit. No obvious gaps for the intended domain.

    Related MCP Connectors

    Related MCP Servers

    • A
      license
      A
      quality
      B
      maintenance
      MCP security server for AI coding agents. 12 tools: pre-install guardian, vulnerability audit, supply-chain attack detection via static code analysis, and CycloneDX 1.6 SBOM generation. Zero runtime dependencies.
      15
      111 npm
      15
      Apache 2.0
    • A
      license
      A
      quality
      D
      maintenance
      MCP server providing dependency and package management tools for AI agents. Analyze licenses, find outdated packages, visualize dependency trees, estimate bundle sizes, and audit security vulnerabilities.
      5
      40 npm
      MIT
    • A
      license
      Not graded
      quality
      C
      maintenance
      Vet a package before your AI coding agent uses it — authoritative facts (CVEs, license, maintenance) via an MCP server + CLI. Local, no account.
      99 npm
      13
      Business Source 1.1
    • A
      license
      Not graded
      quality
      D
      maintenance
      Validates and checks packages across 19 ecosystems to prevent AI agents from installing hallucinated, deprecated, or malicious packages.
      60 npm
      AGPL 3.0